Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4430 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9445. Min Act: -0.1700
Data Index: 6684462 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9286. Min Act: -0.1700
Data Index: 7482919 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9286. Min Act: -0.1700
Data Index: 766474 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8811. Min Act: -0.1700
Data Index: 8270883 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8175. Min Act: -0.1700
Data Index: 4759569 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8016. Min Act: -0.1700
Data Index: 844666 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8016. Min Act: -0.1700
Data Index: 470744 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7857. Min Act: -0.1700
Data Index: 6200355 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8016. Min Act: -0.1700
Data Index: 8227931 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7857. Min Act: -0.1700
Data Index: 7736890 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7857. Min Act: -0.1700
Data Index: 7589721 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7697. Min Act: -0.1700
Data Index: 6257529 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7697. Min Act: -0.1700
Data Index: 6684491 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7697. Min Act: -0.1700
Data Index: 32028 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7857. Min Act: -0.1700
Data Index: 3851276 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7697. Min Act: -0.1700
Data Index: 2913736 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7538. Min Act: -0.1700
Data Index: 647374 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7697. Min Act: -0.1700
Data Index: 6684478 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7538. Min Act: -0.1700
Data Index: 1688568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7538. Min Act: -0.1700
Data Index: 5868143 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19